用 模块化构建
串联PUW工具、Replicate模型及其他工作流。 无限组合。 可通过UI或API运行与分享。
25+ PUW工具
Interior AI、Video AI、3D Gen等，全部可自由组合。
1000+ Replicate模型
SDXL、Stable Diffusion、LLaMA及所有开源模型，无需API密钥。
工作流嵌套
将其他创作者的工作流作为构建模块。他们更新，您的工作流也会同步更新。
将工作流变为应用
将您的AI工作流转化为可分享的应用程序。 无需编码，一键发布。
选择工作流
从您的工作流或社区作品中选择。
选择主题
可选极简、卡片或展示主题。
即时发布
一键上线，随时分享您的应用链接。
免费创建
探索 AI 模型
在您的工作流中直接运行强大的 AI 模型。 无需任何设置。
sdxl-lightning-4step
SDXL-Lightning by ByteDance: a fast text-to-image model that makes high-quality images in 4 steps
flux-schnell
The fastest image generation model tailored for local development and personal use
stable-diffusion
A latent text-to-image diffusion model capable of generating photo-realistic images given any text input
nano-banana
Google's latest image editing model in Gemini 2.5
sdxl
A text-to-image generative AI model that creates beautiful images
flux-kontext-pro
A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language
flux-dev
A 12 billion parameter rectified flow transformer capable of generating images from text descriptions
flux-fast
This is the fastest Flux endpoint in the world.
controlnet-scribble
Generate detailed images from scribbled drawings
z-image-turbo
Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.
seedream-4
Unified text-to-image generation and precise single-sentence editing at up to 4K resolution
flux-1.1-pro-ultra
FLUX1.1 [pro] in ultra and raw modes. Images are up to 4 megapixels. Use raw mode for realism.
nano-banana-pro
Google's state of the art image generation and editing model 🍌🍌
flux-pro
State-of-the-art image generation with top of the line prompt following, visual quality, image detail and output diversity.
proteus-v0.2
Proteus v0.2 shows subtle yet significant improvements over Version 0.1. It demonstrates enhanced prompt understanding that surpasses MJ6, while also approaching its stylistic capabilities.
sdxl-emoji
An SDXL fine-tune based on Apple Emojis
flux-kontext-max
A premium text-based image editing model that delivers maximum performance and improved typography generation for transforming images through natural language prompts
kandinsky-2.2
multilingual text2image latent diffusion model
wan-2.2-i2v-fast
A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B image-to-video
flux-2-klein-4b
Very fast image generation and editing model. 4 steps distilled, sub-second inference for production and near real-time applications.
ideogram-v3-turbo
Turbo is the fastest and cheapest Ideogram v3. v3 creates images with stunning realism, creative designs, and consistent styles
hidream-l1-fast
This is an optimised version of the hidream-l1 model using the pruna ai optimisation toolkit!
recraft-v3
Recraft V3 (code-named red_panda) is a text-to-image model with the ability to generate long texts, and images in a wide list of styles. As of today, it is SOTA in image generation, proven by the Text-to-Image Benchmark by Artificial Analysis
any-comfyui-workflow
Run any ComfyUI workflow. Guide: https://github.com/replicate/cog-comfyui
imagen-4
Google's Imagen 4 flagship model
p-image
A sub 1 second text-to-image model built for production use cases.
gpt-image-1.5
OpenAI's latest image generation model with better instruction following and adherence to prompts
kandinsky-2
text2img model trained on LAION HighRes and fine-tuned on internal datasets
seedream-4.5
Seedream 4.5: Upgraded Bytedance image model with stronger spatial understanding and world knowledge
flux-dev-lora
A version of flux-dev, a text to image model, that supports fast fine-tuned lora inference
它是如何 工作的
构建 AI workflow 应该像连点成线一样简单。我们让它真的如此简单。
上传
拖入您的图片或输入提示词。开始只需要这些。
串联
像搭积木一样连接 AI 模型。每个输出都会流向下一个步骤。
获取结果
一键运行全部流程。多个 AI 工具，即时输出。
把它想象成连接应用，但这是为 AI 而生。
创意AI工具
专业的AI驱动工具，支持图像生成、视频创作、3D建模及创意设计工作流
为什么选择 PUW？
完整的 AI 工作流平台 — 可视化构建、即时托管和用于变现的 marketplace。
| 功能 | Replicate | ComfyUI | N8n | PUW |
|---|---|---|---|---|
| 可视化工作流构建器 | ||||
| 无需编写代码 | ||||
| 多模型链接 | ||||
| 托管基础设施 | ||||
| 内置 marketplace | ||||
| 创作者收益分成 | ||||
| 一键执行 | ||||
| API 访问 | ||||
| 社区模板 | ||||
| AI 原生设计 |
Replicate
ComfyUI
N8n
PUW
PUW 将 ComfyUI 的强大与无代码的简洁结合 — 再加上托管和通过工作流获得收益的 marketplace。
加入 社区
创作者和开发者正在 PUW 上构建 AI 工作流的未来。
"PUW 让串联 AI 模型变得轻松。过去需要几天的工作，现在几分钟就能完成。"
"我在没有写任何代码的情况下，构建了我的第一个 AI 工作流。真正的变革者！"
"可视化构建器非常直观。我可以快速尝试不同的 AI 组合。"
想要 构建并赚钱吗？
构建 AI workflows。发布到 marketplace。每次运行可赚取 70% 的收益。
不断壮大的 社区
加入正在构建 AI workflow 未来的创作者